image_classification

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

• Loss: 1.5890
• Accuracy: 0.5062

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 3e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	10	2.0332	0.25
No log	2.0	20	1.9720	0.3125
No log	3.0	30	1.8937	0.3688
No log	4.0	40	1.8265	0.375
No log	5.0	50	1.7561	0.3937
No log	6.0	60	1.7083	0.45
No log	7.0	70	1.6719	0.4375
No log	8.0	80	1.6415	0.4688
No log	9.0	90	1.6237	0.4813
No log	10.0	100	1.6041	0.4938
No log	11.0	110	1.5890	0.5062
No log	12.0	120	1.5774	0.5
No log	13.0	130	1.5700	0.5
No log	14.0	140	1.5659	0.5062
No log	15.0	150	1.5643	0.5062

Framework versions

• Transformers 4.42.4
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1